Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1975 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.8949. Min Act: -0.1700
Data Index: 947974 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7995. Min Act: -0.1700
Data Index: 1301166 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7676. Min Act: -0.1700
Data Index: 1358186 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7836. Min Act: -0.1700
Data Index: 382733 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7836. Min Act: -0.1700
Data Index: 1223097 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7676. Min Act: -0.1700
Data Index: 604450 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7517. Min Act: -0.1700
Data Index: 360870 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7357. Min Act: -0.1700
Data Index: 563755 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6877. Min Act: -0.1700
Data Index: 270687 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7357. Min Act: -0.1700
Data Index: 1216352 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6877. Min Act: -0.1700
Data Index: 455500 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6717. Min Act: -0.1700
Data Index: 418973 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7037. Min Act: -0.1700
Data Index: 109632 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.7037. Min Act: -0.1700
Data Index: 1018409 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6717. Min Act: -0.1700
Data Index: 883471 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6717. Min Act: -0.1700
Data Index: 1336862 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6717. Min Act: -0.1700
Data Index: 1272617 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6717. Min Act: -0.1700
Data Index: 209065 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6717. Min Act: -0.1700
Data Index: 928770 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8949. Min Range: -2.8949
Max Act: 2.6557. Min Act: -0.1700
Data Index: 269241 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19